Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    reports of criminal activities and legal proceedings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     defe
    -0.76
     dips
    -0.75
     gravy
    -0.69
     quality
    -0.68
     transitions
    -0.68
     constantly
    -0.68
     brief
    -0.67
     pudding
    -0.67
     occasional
    -0.66
     sack
    -0.65
    POSITIVE LOGITS
     Specifically
    1.22
     Yesterday
    1.13
     According
    1.13
     Previously
    1.11
     Speaking
    1.10
     Earlier
    1.04
    Interested
    1.02
     Their
    1.02
     Instead
    1.01
     Though
    1.00
    Act Density 1.147%

    No Known Activations